Context
The user wanted to replicate high-reach posts on LinkedIn. A single-sample prior read (2 likes) had suggested the account was low-engagement, so a full latest-50-post pull was run to get the actual picture before any content decisions.
// Authorized user case
Analyze a LinkedIn account's posts to find replicable high-engagement patterns
A Social Signal Retrieval run that pulled the latest 50 posts of a LinkedIn account, profiled their engagement structure, and extracted content patterns that are replicable for higher engagement.
- Executed
- Tools used
$research-social-signals
Research goal
Analyze the posting behavior of this LinkedIn account and find a replicable method for posts with high readership/engagement.
// Prompt
Original prompt
@skill:Social Signal Retrieval Analyze the posting activity of this account: https://www.linkedin.com/in/xx. The goal is to find a replicable method for producing posts with high readership// Process
What happened
- 01
Pull the latest posts and pin down data boundaries
Fetched the latest 50 posts via get_linkedin_user_posts. Impressions were null on all 50 posts, so engagement (likes, comments, reposts) was used as the available interaction metric; pagination returned the same batch, so older posts were not available.
- 02
Profile the account and the engagement overview
Confirmed the account profile (a market researcher with several hundred followers and 500+ connections; name and company redacted) and computed totals: 295 likes (median 4, max 46), 22 comments on 7 posts, 15 reposts on 7 posts; 34/50 posts with images, 34/50 long-form posts.
- 03
Rank top posts and break down by content type
Ranked the 50 posts by likes+comments+reposts and grouped them into four content types: App rankings (7 posts, avg 15.3 likes, 36% of likes), growth case studies (10, avg 6.6), DTC/brand marketing (13, avg 4.0), and hashtag-only posts (14, avg 2.1).
- 04
Analyze the time trend and content shape
Found a clear strategy turning point: monthly engagement jumped ~4x in June (98 likes) and July (96 likes) 2026, coinciding with the shift from hashtag-only/generic marketing posts to data-driven rankings and growth case studies.
// Evidence
Execution evidence
// Result
What the run showed
- Top post: Appark global App revenue Top 30 (ChatGPT $314M leading) - 46 likes / 6 comments / 2 reposts on 2026-06-11.
- App-ranking posts (7) averaged 15.3 likes and carried 36% of total likes, while hashtag-only posts (14) averaged 2.1 likes - a significant content-type gap.
- Engagement doubled to ~4x from 2026-06 onward, aligning with the shift to data-backed rankings and growth case studies.
- High-engagement posts were consistently image + data-anchored (rankings, growth rates, rank jumps); low-engagement posts were mostly image-less hashtag-only posts.
- Corrected the earlier single-sample conclusion: absolute engagement is still low (avg 6.4 likes), but the account has a clear relative high-engagement content line.
Tools used
$research-social-signals